In this notebook, some template code has already been provided for you, and you will need to implement additional functionality to successfully complete this project. You will not need to modify the included code beyond what is requested. Sections that begin with '(IMPLEMENTATION)' in the header indicate that the following block of code will require additional functionality which you must provide. Instructions will be provided for each section, and the specifics of the implementation are marked in the code block with a 'TODO' statement. Please be sure to read the instructions carefully!
Note: Once you have completed all of the code implementations, you need to finalize your work by exporting the Jupyter Notebook as an HTML document. Before exporting the notebook to html, all of the code cells need to have been run so that reviewers can see the final implementation and output. You can then export the notebook by using the menu above and navigating to File -> Download as -> HTML (.html). Include the finished document along with this notebook as your submission.
In addition to implementing code, there will be questions that you must answer which relate to the project and your implementation. Each section where you will answer a question is preceded by a 'Question X' header. Carefully read each question and provide thorough answers in the following text boxes that begin with 'Answer:'. Your project submission will be evaluated based on your answers to each of the questions and the implementation you provide.
Note: Code and Markdown cells can be executed using the Shift + Enter keyboard shortcut. Markdown cells can be edited by double-clicking the cell to enter edit mode.
The rubric contains optional "Stand Out Suggestions" for enhancing the project beyond the minimum requirements. If you decide to pursue the "Stand Out Suggestions", you should include the code in this Jupyter notebook.
In this notebook, you will make the first steps towards developing an algorithm that could be used as part of a mobile or web app. At the end of this project, your code will accept any user-supplied image as input. If a dog is detected in the image, it will provide an estimate of the dog's breed. If a human is detected, it will provide an estimate of the dog breed that is most resembling. The image below displays potential sample output of your finished project (... but we expect that each student's algorithm will behave differently!).

In this real-world setting, you will need to piece together a series of models to perform different tasks; for instance, the algorithm that detects humans in an image will be different from the CNN that infers dog breed. There are many points of possible failure, and no perfect algorithm exists. Your imperfect solution will nonetheless create a fun user experience!
We break the notebook into separate steps. Feel free to use the links below to navigate the notebook.
Make sure that you've downloaded the required human and dog datasets:
Note: if you are using the Udacity workspace, you DO NOT need to re-download these - they can be found in the /data folder as noted in the cell below.
Download the dog dataset. Unzip the folder and place it in this project's home directory, at the location /dog_images.
Download the human dataset. Unzip the folder and place it in the home directory, at location /lfw.
Note: If you are using a Windows machine, you are encouraged to use 7zip to extract the folder.
In the code cell below, we save the file paths for both the human (LFW) dataset and dog dataset in the numpy arrays human_files and dog_files.
import numpy as np
from glob import glob
from pandas import DataFrame
# load filenames for human and dog images
human_files = np.array(glob("/data/lfw/*/*"))
dog_files = np.array(glob("/data/dog_images/*/*/*"))
# print number of images in each dataset
print('There are %d total human images.' % len(human_files))
print('There are %d total dog images.' % len(dog_files))
In this section, we use OpenCV's implementation of Haar feature-based cascade classifiers to detect human faces in images.
OpenCV provides many pre-trained face detectors, stored as XML files on github. We have downloaded one of these detectors and stored it in the haarcascades directory. In the next code cell, we demonstrate how to use this detector to find human faces in a sample image.
import cv2
import matplotlib.pyplot as plt
%matplotlib inline
# extract pre-trained face detector
face_cascade = cv2.CascadeClassifier('haarcascades/haarcascade_frontalface_alt.xml')
# load color (BGR) image
img = cv2.imread(human_files[0])
# convert BGR image to grayscale
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# find faces in image
faces = face_cascade.detectMultiScale(gray)
# print number of faces detected in the image
print('Number of faces detected:', len(faces))
# get bounding box for each detected face
for (x,y,w,h) in faces:
# add bounding box to color image
cv2.rectangle(img,(x,y),(x+w,y+h),(255,0,0),2)
# convert BGR image to RGB for plotting
cv_rgb = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
# display the image, along with bounding box
plt.imshow(cv_rgb)
plt.show()
Before using any of the face detectors, it is standard procedure to convert the images to grayscale. The detectMultiScale function executes the classifier stored in face_cascade and takes the grayscale image as a parameter.
In the above code, faces is a numpy array of detected faces, where each row corresponds to a detected face. Each detected face is a 1D array with four entries that specifies the bounding box of the detected face. The first two entries in the array (extracted in the above code as x and y) specify the horizontal and vertical positions of the top left corner of the bounding box. The last two entries in the array (extracted here as w and h) specify the width and height of the box.
We can use this procedure to write a function that returns True if a human face is detected in an image and False otherwise. This function, aptly named face_detector, takes a string-valued file path to an image as input and appears in the code block below.
# returns "True" if face is detected in image stored at img_path
def face_detector(img_path):
img = cv2.imread(img_path)
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
faces = face_cascade.detectMultiScale(gray)
return len(faces) > 0
Question 1: Use the code cell below to test the performance of the face_detector function.
human_files have a detected human face? dog_files have a detected human face? Ideally, we would like 100% of human images with a detected face and 0% of dog images with a detected face. You will see that our algorithm falls short of this goal, but still gives acceptable performance. We extract the file paths for the first 100 images from each of the datasets and store them in the numpy arrays human_files_short and dog_files_short.
Answer: human: 98% dog: 98%
from tqdm import tqdm
human_files_short = human_files[:100]
dog_files_short = dog_files[:100]
#-#-# Do NOT modify the code above this line. #-#-#
## TODO: Test the performance of the face_detector algorithm
human_running_loss = 0
human_loss = 0
dog_running_loss = 0
dog_loss = 0
#create arrays that will hold string results (true/false)
human_result = ["string"] * len(human_files_short)
dog_result = ["string"] * len(dog_files_short)
for i in range(len(human_files_short)):
human_result[i] = face_detector(human_files_short[i])
if human_result[i] == False:
human_loss = 1
human_running_loss += human_loss
dog_result[i] = face_detector(dog_files_short[i])
if dog_result[i] == False:
dog_loss = 1
dog_running_loss += dog_loss
human_accuracy = human_result.count(True) / len(human_files_short)
dog_accuracy = human_result.count(True) / len(human_files_short)
print("Prediction accuracy - human: {:.3f}".format(human_accuracy))
print("Prediction accuracy - dog: {:.3f}".format(dog_accuracy))
## on the images in human_files_short and dog_files_short.
We suggest the face detector from OpenCV as a potential way to detect human images in your algorithm, but you are free to explore other approaches, especially approaches that make use of deep learning :). Please use the code cell below to design and test your own face detection algorithm. If you decide to pursue this optional task, report performance on human_files_short and dog_files_short.
### (Optional)
### TODO: Test performance of anotherface detection algorithm.
### Feel free to use as many code cells as needed.
In this section, we use a pre-trained model to detect dogs in images.
The code cell below downloads the VGG-16 model, along with weights that have been trained on ImageNet, a very large, very popular dataset used for image classification and other vision tasks. ImageNet contains over 10 million URLs, each linking to an image containing an object from one of 1000 categories.
import torch
import torchvision.models as models
# define VGG16 model
VGG16 = models.vgg16(pretrained=True)
# check if CUDA is available
use_cuda = torch.cuda.is_available()
# move model to GPU if CUDA is available
if use_cuda:
VGG16 = VGG16.cuda()
Given an image, this pre-trained VGG-16 model returns a prediction (derived from the 1000 possible categories in ImageNet) for the object that is contained in the image.
In the next code cell, you will write a function that accepts a path to an image (such as 'dogImages/train/001.Affenpinscher/Affenpinscher_00001.jpg') as input and returns the index corresponding to the ImageNet class that is predicted by the pre-trained VGG-16 model. The output should always be an integer between 0 and 999, inclusive.
Before writing the function, make sure that you take the time to learn how to appropriately pre-process tensors for pre-trained models in the PyTorch documentation.
#import helper
from PIL import Image
#ImageFile.LOAD_TRUNCATED_IMAGES = True
from torchvision import datasets, transforms
#added
import os
from pandas import DataFrame
import torch.nn as nn
import torch.optim as optim
import torchvision
import torch
def VGG16_predict(img_path):
'''
Use pre-trained VGG-16 model to obtain index corresponding to
predicted ImageNet class for image at specified path
Args:
img_path: path to an image
Returns:
Index corresponding to VGG-16 model's prediction
'''
#'dogImages/train/001.Affenpinscher/Affenpinscher_00001.jpg'
#open the img
img = Image.open(img_path)
## TODO: Complete the function.
transform = transforms.Compose([transforms.RandomRotation(30),
transforms.RandomResizedCrop(224),
transforms.RandomHorizontalFlip(),
transforms.ToTensor()])
image = transform(img).unsqueeze_(0)
if use_cuda:
image = image.cuda()
VGG16.eval() # to put in eval mode as we are only doing inference
output = torch.argmax(VGG16(image)).item()
# output2 = VGG16(image)
return output # predicted class index
#VGG16_predict('/data/dog_images/train/001.Affenpinscher/Affenpinscher_00001.jpg')
While looking at the dictionary, you will notice that the categories corresponding to dogs appear in an uninterrupted sequence and correspond to dictionary keys 151-268, inclusive, to include all categories from 'Chihuahua' to 'Mexican hairless'. Thus, in order to check to see if an image is predicted to contain a dog by the pre-trained VGG-16 model, we need only check if the pre-trained model predicts an index between 151 and 268 (inclusive).
Use these ideas to complete the dog_detector function below, which returns True if a dog is detected in an image (and False if not).
### returns "True" if a dog is detected in the image stored at img_path
def dog_detector(img_path):
## TODO: Complete the function.
output = VGG16_predict(img_path)
if output > 150 and output < 269:
output2 = True
else:
output2 = False
return output2 # true/false
Question 2: Use the code cell below to test the performance of your dog_detector function.
human_files_short have a detected dog? dog_files_short have a detected dog?Answer: 2% in both human and dog
### TODO: Test the performance of the dog_detector function
### on the images in human_files_short and dog_files_short.
human_running_loss = 0
human_loss = 0
dog_running_loss = 0
dog_loss = 0
human_result = ["string"] * len(human_files_short)
dog_result = ["string"] * len(dog_files_short)
for i in range(len(human_files_short)):
human_result[i] = dog_detector(human_files_short[i])
if human_result[i] == False:
human_loss = 1
human_running_loss += human_loss
dog_result[i] = dog_detector(dog_files_short[i])
if dog_result[i] == False:
dog_loss = 1
dog_running_loss += dog_loss
human_accuracy = human_result.count(True) / len(human_files_short)
dog_accuracy = human_result.count(True) / len(human_files_short)
print("Prediction accuracy - human: {:.6f}".format(human_accuracy))
print("Prediction accuracy - dog: {:.6f}".format(dog_accuracy))
We suggest VGG-16 as a potential network to detect dog images in your algorithm, but you are free to explore other pre-trained networks (such as Inception-v3, ResNet-50, etc). Please use the code cell below to test other pre-trained PyTorch models. If you decide to pursue this optional task, report performance on human_files_short and dog_files_short.
### (Optional)
### TODO: Report the performance of another pre-trained network.
### Feel free to use as many code cells as needed.
Now that we have functions for detecting humans and dogs in images, we need a way to predict breed from images. In this step, you will create a CNN that classifies dog breeds. You must create your CNN from scratch (so, you can't use transfer learning yet!), and you must attain a test accuracy of at least 10%. In Step 4 of this notebook, you will have the opportunity to use transfer learning to create a CNN that attains greatly improved accuracy.
We mention that the task of assigning breed to dogs from images is considered exceptionally challenging. To see why, consider that even a human would have trouble distinguishing between a Brittany and a Welsh Springer Spaniel.
| Brittany | Welsh Springer Spaniel |
|---|---|
![]() |
![]() |
It is not difficult to find other dog breed pairs with minimal inter-class variation (for instance, Curly-Coated Retrievers and American Water Spaniels).
| Curly-Coated Retriever | American Water Spaniel |
|---|---|
![]() |
![]() |
Likewise, recall that labradors come in yellow, chocolate, and black. Your vision-based algorithm will have to conquer this high intra-class variation to determine how to classify all of these different shades as the same breed.
| Yellow Labrador | Chocolate Labrador | Black Labrador |
|---|---|---|
![]() |
![]() |
![]() |
We also mention that random chance presents an exceptionally low bar: setting aside the fact that the classes are slightly imabalanced, a random guess will provide a correct answer roughly 1 in 133 times, which corresponds to an accuracy of less than 1%.
Remember that the practice is far ahead of the theory in deep learning. Experiment with many different architectures, and trust your intuition. And, of course, have fun!
Use the code cell below to write three separate data loaders for the training, validation, and test datasets of dog images (located at dog_images/train, dog_images/valid, and dog_images/test, respectively). You may find this documentation on custom datasets to be a useful resource. If you are interested in augmenting your training and/or validation data, check out the wide variety of transforms!
import os
from torchvision import datasets
from PIL import ImageFile
ImageFile.LOAD_TRUNCATED_IMAGES = True
### TODO: Write data loaders for training, validation, and test sets
data_dir = '/data/dog_images/'
train_dir = os.path.join(data_dir, 'train')
test_dir = os.path.join(data_dir, 'test')
valid_dir = os.path.join(data_dir, 'valid')
## Specify appropriate transforms, and batch_sizes
data_transform = transforms.Compose([transforms.RandomRotation(30),
transforms.RandomResizedCrop(256),
transforms.RandomHorizontalFlip(),
transforms.ToTensor()])
train_data = datasets.ImageFolder(train_dir, transform = data_transform)
test_data = datasets.ImageFolder(test_dir, transform = data_transform)
valid_data = datasets.ImageFolder(valid_dir, transform = data_transform)
batch_size = 20
num_workers = 0
#train_loader = torch.utils.data.DataLoader(train_data, batch_size=batch_size, num_workers=num_workers, shuffle = True)
#test_loader = torch.utils.data.DataLoader(test_data, batch_size=batch_size, num_workers=num_workers, shuffle = True)
#valid_loader = torch.utils.data.DataLoader(valid_data, batch_size=batch_size, num_workers=num_workers, shuffle = True)
loaders_scratch={'train':torch.utils.data.DataLoader(train_data, batch_size=batch_size, num_workers=num_workers, shuffle = True),
'test':torch.utils.data.DataLoader(test_data, batch_size=batch_size, num_workers=num_workers, shuffle = True),
'valid':torch.utils.data.DataLoader(valid_data, batch_size=batch_size, num_workers=num_workers, shuffle = True)}
Question 3: Describe your chosen procedure for preprocessing the data.
Answer: Resizing done by cropping. The input tensor size is 32 - in line with CNN below required inputs Yes - augmented the dataset with rotations and horizontal flips.
Create a CNN to classify dog breed. Use the template in the code cell below.
import torch.nn as nn
import torch.nn.functional as F
# define the CNN architecture
class Net(nn.Module):
### TODO: choose an architecture, and complete the class
def __init__(self):
super(Net, self).__init__()
## Define layers of a CNN
# convolutional layer (sees 256x256x3 image tensor)
self.conv1 = nn.Conv2d(3, 8, 3, padding=1)
# convolutional layer (sees 128x128x3 image tensor)
self.conv2 = nn.Conv2d(8, 16, 3, padding=1)
# convolutional layer (sees 64x64x16 tensor)
self.conv3 = nn.Conv2d(16, 32, 3, padding=1)
# convolutional layer (sees 32x32x32 tensor)
self.conv4 = nn.Conv2d(32, 64, 3, padding=1)
# convolutional layer (sees 16x16x64 tensor)
self.conv5 = nn.Conv2d(64, 128, 3, padding=1)
# convolutional layer (sees 8x8x128 tensor)
self.conv6 = nn.Conv2d(128, 256, 3, padding=1)
# max pooling layer
self.pool = nn.MaxPool2d(2, 2)
# linear layer (256 * 4 * 4 -> 500)
self.fc1 = nn.Linear(256 * 4 * 4, 2000)
# linear layer (2000 -> 500)
self.fc2 = nn.Linear(2000, 500)
#linear layer (500 -> 133)
self.fc3 = nn.Linear(500, 133)
# dropout layer (p=0.25)
self.dropout = nn.Dropout(0.25)
def forward(self, x):
## Define forward behavior
x = self.pool(F.relu(self.conv1(x)))
x = self.pool(F.relu(self.conv2(x)))
x = self.pool(F.relu(self.conv3(x)))
x = self.pool(F.relu(self.conv4(x)))
x = self.pool(F.relu(self.conv5(x)))
x = self.pool(F.relu(self.conv6(x)))
# flatten image input
x = x.view(-1, 256 * 4 * 4)
# add dropout layer
x = self.dropout(x)
# add 1st hidden layer, with relu activation function
x = F.relu(self.fc1(x))
# add dropout layer
x = self.dropout(x)
# add 2nd hidden layer, with relu activation function
x = self.fc2(x)
# add dropout layer
x = self.dropout(x)
# add 2nd hidden layer, with relu activation function
x = self.fc3(x)
return x
#-#-# You so NOT have to modify the code below this line. #-#-#
# instantiate the CNN
model_scratch = Net()
# move tensors to GPU if CUDA is available
if use_cuda:
model_scratch.cuda()
Question 4: Outline the steps you took to get to your final CNN architecture and your reasoning at each step.
Answer: Based on CIFAR structure to start with:
Input: 256x256 pixel by 3 (for RGB). Tried to get as close to actual dog picture sizes - which are around 400+ pixels
Layer 1 Convolutional layer: takes in an input of 3 (RGB) and want the output to be 8. Kernel size is 3 with padding of 1
Maxpool 1: turns the 256 by 256 pixel image into a 128 x 128 image, with a depth of 8
Layer 2 Convolutional layer: takes the input from maxpool 1 and turns it into an output of 16. Kernel size and padding unchanged
Maxpool 2: turns the 128 by 128 pixel image into an 64 x 64 image, with a depth of 16
Layer 3 Convolutional layer: takes in an input of 3 (RGB) and want the output to be 32. Kernel size is 3 with padding of 1
Maxpool 3: turns the 64 by 64 pixel image into a 32 x 32 image, with a depth of 32
Layer 4 Convolutional layer: takes the input from maxpool 3 and turns it into an output of 64. Kernel size and padding unchanged
Maxpool 4: turns the 32 by 32 pixel image into an 16 x 16 image, with a depth of 64
Layer 5 Convolutional layer: takes the input from maxpool 4 and turns it into an output of 128. Kernel size and padding unchanged.
Maxpool 5: turns the 16 by 16 image into a 8 by 8 image, depth stays at 128.
Layer 6 Convolutional layer: takes the input from maxpool 5 and turns it into an output of 256. Kernel size and padding unchanged.
Maxpool 6: turns the 8 by 8 image into a 8 by 8 image, depth stays at 256.
Now the output is flattened so we can put it into a fully connected layer. Note that the dimension of the first fully connected layer is the depth from layer 3 convolutional layer (64) multiplied by 4 x 4
Dropout layers interleaved before and after the 1st fully connected layer to discourage overfitting.
Use the next code cell to specify a loss function and optimizer. Save the chosen loss function as criterion_scratch, and the optimizer as optimizer_scratch below.
import torch.optim as optim
### TODO: select loss function
criterion_scratch = nn.CrossEntropyLoss()
### TODO: select optimizer
optimizer_scratch = optim.SGD(model_scratch.parameters(), lr = 0.01)
Train and validate your model in the code cell below. Save the final model parameters at filepath 'model_scratch.pt'.
def train(n_epochs, loaders, model, optimizer, criterion, use_cuda, save_path):
"""returns trained model"""
# initialize tracker for minimum validation loss
valid_loss_min = np.Inf
for epoch in range(1, n_epochs+1):
# initialize variables to monitor training and validation loss
train_loss = 0.0
valid_loss = 0.0
###################
# train the model #
###################
model.train()
for batch_idx, (data, target) in enumerate(loaders['train']):
# move to GPU
if use_cuda:
data, target = data.cuda(), target.cuda()
## find the loss and update the model parameters accordingly
#clear gradients
optimizer_scratch.zero_grad()
#forward pass
output = model_scratch(data)
# calculate the batch loss
loss = criterion(output, target)
#backward pass
loss.backward()
#update parameters
optimizer_scratch.step()
#train_loss updated
#train_loss += loss.item()*data.size(0)
## record the average training loss, using something like
train_loss = train_loss + ((1 / (batch_idx + 1)) * (loss.data - train_loss))
######################
# validate the model #
######################
model.eval()
for batch_idx, (data, target) in enumerate(loaders['valid']):
# move to GPU
if use_cuda:
data, target = data.cuda(), target.cuda()
## update the average validation loss
valid_loss = valid_loss + ((1 / (batch_idx + 1)) * (loss.data - valid_loss))
# print training/validation statistics
print('Epoch: {} \tTraining Loss: {:.6f} \tValidation Loss: {:.6f}'.format(
epoch,
train_loss,
valid_loss
))
## TODO: save the model if validation loss has decreased
if valid_loss <= valid_loss_min:
print('Validation loss decreased --> ',
'Saving model ...'.format(valid_loss_min,
valid_loss))
torch.save(model_scratch.state_dict(), 'model_scratch.pt')
valid_loss_min = valid_loss
# return trained model
return model
# train the model
model_scratch = train(100, loaders_scratch, model_scratch, optimizer_scratch,
criterion_scratch, use_cuda, 'model_scratch.pt')
# load the model that got the best validation accuracy
model_scratch.load_state_dict(torch.load('model_scratch.pt'))
Try out your model on the test dataset of dog images. Use the code cell below to calculate and print the test loss and accuracy. Ensure that your test accuracy is greater than 10%.
def test(loaders, model, criterion, use_cuda):
# monitor test loss and accuracy
test_loss = 0.
correct = 0.
total = 0.
model.eval()
for batch_idx, (data, target) in enumerate(loaders['test']):
# move to GPU
if use_cuda:
data, target = data.cuda(), target.cuda()
# forward pass: compute predicted outputs by passing inputs to the model
output = model(data)
# calculate the loss
loss = criterion(output, target)
# update average test loss
test_loss = test_loss + ((1 / (batch_idx + 1)) * (loss.data - test_loss))
# convert output probabilities to predicted class
pred = output.data.max(1, keepdim=True)[1]
# compare predictions to true label
correct += np.sum(np.squeeze(pred.eq(target.data.view_as(pred))).cpu().numpy())
total += data.size(0)
print('Test Loss: {:.6f}\n'.format(test_loss))
print('\nTest Accuracy: %2d%% (%2d/%2d)' % (
100. * correct / total, correct, total))
# call test function
test(loaders_scratch, model_scratch, criterion_scratch, use_cuda)
You will now use transfer learning to create a CNN that can identify dog breed from images. Your CNN must attain at least 60% accuracy on the test set.
Use the code cell below to write three separate data loaders for the training, validation, and test datasets of dog images (located at dogImages/train, dogImages/valid, and dogImages/test, respectively).
If you like, you are welcome to use the same data loaders from the previous step, when you created a CNN from scratch.
## TODO: Specify data loaders
import os
from torchvision import datasets
from PIL import ImageFile
ImageFile.LOAD_TRUNCATED_IMAGES = True
### TODO: Write data loaders for training, validation, and test sets
data_dir = '/data/dog_images/'
train_dir = os.path.join(data_dir, 'train')
test_dir = os.path.join(data_dir, 'test')
valid_dir = os.path.join(data_dir, 'valid')
## Specify appropriate transforms, and batch_sizes
data_transform = transforms.Compose([transforms.RandomRotation(30),
transforms.RandomResizedCrop(224), #need this for VGG16!
transforms.RandomHorizontalFlip(),
transforms.ToTensor()])
train_data = datasets.ImageFolder(train_dir, transform = data_transform)
test_data = datasets.ImageFolder(test_dir, transform = data_transform)
valid_data = datasets.ImageFolder(valid_dir, transform = data_transform)
batch_size = 20
num_workers = 0
#train_loader = torch.utils.data.DataLoader(train_data, batch_size=batch_size, num_workers=num_workers, shuffle = True)
#test_loader = torch.utils.data.DataLoader(test_data, batch_size=batch_size, num_workers=num_workers, shuffle = True)
#valid_loader = torch.utils.data.DataLoader(valid_data, batch_size=batch_size, num_workers=num_workers, shuffle = True)
loaders_transfer={'train':torch.utils.data.DataLoader(train_data, batch_size=batch_size, num_workers=num_workers, shuffle = True),
'test':torch.utils.data.DataLoader(test_data, batch_size=batch_size, num_workers=num_workers, shuffle = True),
'valid':torch.utils.data.DataLoader(valid_data, batch_size=batch_size, num_workers=num_workers, shuffle = True)}
Use transfer learning to create a CNN to classify dog breed. Use the code cell below, and save your initialized model as the variable model_transfer.
import torchvision.models as models
import torch.nn as nn
import torch.optim as optim
## TODO: Specify model architecture
# Load the pretrained model from pytorch
model_transfer = models.vgg16(pretrained=True)
# print out the model structure
print(model_transfer)
# Freeze training for all "features" layers
for param in model_transfer.features.parameters():
param.requires_grad = False
n_inputs = model_transfer.classifier[6].in_features
# add last linear layer (n_inputs -> 133 dog breeds)
# new layers automatically have requires_grad = True
last_layer = nn.Linear(n_inputs, 133)
model_transfer.classifier[6] = last_layer
# check to see that your last layer produces the expected number of outputs
print(model_transfer.classifier[6].in_features)
print(model_transfer.classifier[6].out_features)
print(model_transfer)
if use_cuda:
model_transfer = model_transfer.cuda()
#save the model structure
torch.save(model_transfer.state_dict(), 'model_transfer.pt')
Question 5: Outline the steps you took to get to your final CNN architecture and your reasoning at each step. Describe why you think the architecture is suitable for the current problem.
Answer: Ensured that the input is of size 224, in line with what VGG needs Ensured that the output no. of classes matched the no. of breeds
Use the next code cell to specify a loss function and optimizer. Save the chosen loss function as criterion_transfer, and the optimizer as optimizer_transfer below.
criterion_transfer = nn.CrossEntropyLoss()
optimizer_transfer = optim.SGD(model_transfer.classifier.parameters(), lr=0.001)
Train and validate your model in the code cell below. Save the final model parameters at filepath 'model_transfer.pt'.
def transfer_train(n_epochs, loaders, model, optimizer, criterion, use_cuda, save_path):
# initialize tracker for minimum validation loss
valid_loss_min = np.Inf
for epoch in range(1, n_epochs+1):
# keep track of training and validation loss
train_loss = 0.0
valid_loss = 0.0
###################
# train the model #
###################
# model by default is set to train
for batch_i, (data, target) in enumerate(loaders_transfer['train']):
# move tensors to GPU if CUDA is available
if use_cuda:
data, target = data.cuda(), target.cuda()
# clear the gradients of all optimized variables
optimizer_transfer.zero_grad()
# forward pass: compute predicted outputs by passing inputs to the model
output = model_transfer(data)
# calculate the batch loss
loss = criterion_transfer(output, target)
# backward pass: compute gradient of the loss with respect to model parameters
loss.backward()
# perform a single optimization step (parameter update)
optimizer_transfer.step()
# update training loss
train_loss += loss.item()
if batch_i % 20 == 19: # print training loss every specified number of mini-batches
print('Epoch %d, Batch %d loss: %.16f' %
(epoch, batch_i + 1, train_loss / 20))
train_loss = 0.0
######################
# validate the model #
######################
model_transfer.eval()
for batch_i, (data, target) in enumerate(loaders_transfer['valid']):
# move to GPU
if use_cuda:
data, target = data.cuda(), target.cuda()
## update the average validation loss
valid_loss = valid_loss + ((1 / (batch_i + 1)) * (loss.data - valid_loss))
# print training/validation statistics
print('Epoch: {} \tTraining Loss: {:.6f} \tValidation Loss: {:.6f}'.format(
epoch,
train_loss,
valid_loss
))
## TODO: save the model if validation loss has decreased
if valid_loss <= valid_loss_min:
print('Validation loss decreased --> ',
'Saving model ...'.format(valid_loss_min,
valid_loss))
torch.save(model_transfer.state_dict(), 'model_transfer.pt')
valid_loss_min = valid_loss
return model_transfer
#model_transfer.load_state_dict(torch.load('model_transfer.pt'))
# train the model
transfer_train(50, loaders_transfer, model_transfer, optimizer_transfer, criterion_transfer, use_cuda, 'model_transfer.pt')
# load the model that got the best validation accuracy
model_transfer.load_state_dict(torch.load('model_transfer.pt'))
Try out your model on the test dataset of dog images. Use the code cell below to calculate and print the test loss and accuracy. Ensure that your test accuracy is greater than 60%.
def test_transfer(loaders, model, criterion, use_cuda):
# monitor test loss and accuracy
test_loss = 0.
correct = 0.
total = 0.
model_transfer.eval()
for batch_i, (data, target) in enumerate(loaders_transfer['test']):
# move to GPU
if use_cuda:
data, target = data.cuda(), target.cuda()
# forward pass: compute predicted outputs by passing inputs to the model
output = model_transfer(data)
# calculate the loss
loss = criterion_transfer(output, target)
# update average test loss
test_loss = test_loss + ((1 / (batch_i + 1)) * (loss.data - test_loss))
# convert output probabilities to predicted class
pred = output.data.max(1, keepdim=True)[1]
# compare predictions to true label
correct += np.sum(np.squeeze(pred.eq(target.data.view_as(pred))).cpu().numpy())
total += data.size(0)
print('Test Loss: {:.6f}\n'.format(test_loss))
print('\nTest Accuracy: %2d%% (%2d/%2d)' % (
100. * correct / total, correct, total))
# call test function
test_transfer(loaders_transfer, model_transfer, criterion_transfer, use_cuda)
Write a function that takes an image path as input and returns the dog breed (Affenpinscher, Afghan hound, etc) that is predicted by your model.
### TODO: Write a function that takes a path to an image as input
### and returns the dog breed that is predicted by the model.
from PIL import Image
ImageFile.LOAD_TRUNCATED_IMAGES = True
from torchvision import datasets, transforms
from PIL import Image
data = {"train" : train_data, "valid" : valid_data, "test" : test_data}
data_transfer = data
# list of class names by index, i.e. a name can be accessed like class_names[0]
class_names = [item[4:].replace("_", " ") for item in data_transfer['train'].classes]
def predict_breed_transfer(img_path):
# load the image and return the predicted breed
img_transform = transforms.Compose([transforms.Resize((224,224)),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406],
[0.229, 0.224, 0.225])
])
img = Image.open(img_path)
img = img_transform(img).unsqueeze(0)
if use_cuda:
img = img.cuda()
model_transfer.eval()
output = model_transfer(img)
prediction = output.argmax().item()
breed_prediction = class_names[prediction]
return breed_prediction
predict_breed_transfer('/data/dog_images/train/001.Affenpinscher/Affenpinscher_00001.jpg')
Write an algorithm that accepts a file path to an image and first determines whether the image contains a human, dog, or neither. Then,
You are welcome to write your own functions for detecting humans and dogs in images, but feel free to use the face_detector and human_detector functions developed above. You are required to use your CNN from Step 4 to predict dog breed.
Some sample output for our algorithm is provided below, but feel free to design your own user experience!

### TODO: Write your algorithm.
### Feel free to use as many code cells as needed.
import matplotlib.pyplot as plt
%matplotlib inline
def run_app(img_path):
## handle cases for a human face, dog, and neither
img = Image.open(img_path)
# display the image
plt.imshow(img)
plt.show()
if dog_detector(img_path)==True:
output = print('Dog breed detected:', predict_breed_transfer(img_path))
elif face_detector(img_path)==True:
output = print('Human detected: looks like a ...', predict_breed_transfer(img_path))
else:
output = print("Error - image is not a dog or a human")
return output
In this section, you will take your new algorithm for a spin! What kind of dog does the algorithm think that you look like? If you have a dog, does it predict your dog's breed accurately? If you have a cat, does it mistakenly think that your cat is a dog?
Test your algorithm at least six images on your computer. Feel free to use any images you like. Use at least two human and two dog images.
Question 6: Is the output better than you expected :) ? Or worse :( ? Provide at least three possible points of improvement for your algorithm.
Answer:
I could use batch normalization to further improve the performance of the model. Increase the number of epochs, as we still see a decrease in validation loss after only 50. Increase the learning rate slightly to have model learn faster.
## TODO: Execute your algorithm from Step 6 on
## at least 6 images on your computer.
## Feel free to use as many code cells as needed.
import numpy as np
for file in np.hstack((human_files[0:25], dog_files[0:25])):
run_app(file)